The conversation machine comprehension(MC)task aims to answer questions in the multi-turn conversation for a single passage.However,recent approaches don’t exploit information from historical conversations effectivel...The conversation machine comprehension(MC)task aims to answer questions in the multi-turn conversation for a single passage.However,recent approaches don’t exploit information from historical conversations effectively,which results in some references and ellipsis in the current question cannot be recognized.In addition,these methods do not consider the rich semantic relationships between words when reasoning about the passage text.In this paper,we propose a novel model GraphFlow+,which constructs a context graph for each conversation turn and uses a unique recurrent graph neural network(GNN)to model the temporal dependencies between the context graphs of each turn.Specifically,we exploit three different ways to construct text graphs,including the dynamic graph,static graph,and hybrid graph that combines the two.Our experiments on CoQA,QuAC and DoQA show that the GraphFlow+model can outperform the state-of-the-art approaches.展开更多
Sampling-based path planning is widely used in robotics,particularly in high-dimensional state spaces.In the path planning process,collision detection is the most time-consuming operation.Therefore,we propose a learni...Sampling-based path planning is widely used in robotics,particularly in high-dimensional state spaces.In the path planning process,collision detection is the most time-consuming operation.Therefore,we propose a learning-based path planning method that reduces the number of collision checks.We develop an efficient neural network model based on graph neural networks.The model outputs weights for each neighbor based on the obstacle,searched path,and random geometric graph,which are used to guide the planner in avoiding obstacles.We evaluate the efficiency of the proposed path planning method through simulated random worlds and real-world experiments.The results demonstrate that the proposed method significantly reduces the number of collision checks and improves the path planning speed in high-dimensional environments.展开更多
Graph convolutional networks(GCNs)have received significant attention from various research fields due to the excellent performance in learning graph representations.Although GCN performs well compared with other meth...Graph convolutional networks(GCNs)have received significant attention from various research fields due to the excellent performance in learning graph representations.Although GCN performs well compared with other methods,it still faces challenges.Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs.Therefore,motivated by an urgent need in terms of efficiency and scalability in training GCN,sampling methods have been proposed and achieved a significant effect.In this paper,we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN.To highlight the characteristics and differences of sampling methods,we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories.Finally,we discuss some challenges and future research directions of the sampling methods.展开更多
The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the spotlight.Most exi...The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the spotlight.Most existing frameworks typically utilize separate modules for spatial and temporal correlations modeling.However,this stepwise pattern may limit the effectiveness and efficiency in spatial-temporal feature extraction and cause the overlook of important information in some steps.Furthermore,it is lacking sufficient guidance from prior information while modeling based on a given spatial adjacency graph(e.g.,deriving from the geodesic distance or approximate connectivity),and may not reflect the actual interaction between nodes.To overcome those limitations,our paper proposes a spatial-temporal graph synchronous aggregation(STGSA)model to extract the localized and long-term spatial-temporal dependencies simultaneously.Specifically,a tailored graph aggregation method in the vertex domain is designed to extract spatial and temporal features in one graph convolution process.In each STGSA block,we devise a directed temporal correlation graph to represent the localized and long-term dependencies between nodes,and the potential temporal dependence is further fine-tuned by an adaptive weighting operation.Meanwhile,we construct an elaborated spatial adjacency matrix to represent the road sensor graph by considering both physical distance and node similarity in a datadriven manner.Then,inspired by the multi-head attention mechanism which can jointly emphasize information from different r epresentation subspaces,we construct a multi-stream module based on the STGSA blocks to capture global information.It projects the embedding input repeatedly with multiple different channels.Finally,the predicted values are generated by stacking several multi-stream modules.Extensive experiments are constructed on six real-world datasets,and numerical results show that the proposed STGSA model significantly outperforms the benchmarks.展开更多
Numerous meta-learning methods focus on the few-shot learning issue,yet most of them assume that various tasks have a shared embedding space,so the generalization ability of the trained model is limited.In order to so...Numerous meta-learning methods focus on the few-shot learning issue,yet most of them assume that various tasks have a shared embedding space,so the generalization ability of the trained model is limited.In order to solve the aforementioned problem,a task-adaptive meta-learning method based on graph neural network(TAGN) is proposed in this paper,where the characterization ability of the original feature extraction network is ameliorated and the classification accuracy is remarkably improved.Firstly,a task-adaptation module based on the self-attention mechanism is employed,where the generalization ability of the model is enhanced on the new task.Secondly,images are classified in non-Euclidean domain,where the disadvantages of poor adaptability of the traditional distance function are overcome.A large number of experiments are conducted and the results show that the proposed methodology has a better performance than traditional task-independent classification methods on two real-word datasets.展开更多
现有的大多数兴趣点(point of interest,POI)推荐系统由于忽略了用户签到序列中的顺序行为模式,以及用户的个性化偏好对于POI推荐的影响,导致POI推荐系统性能较低,推荐结果不可靠,进而影响用户体验。为了解决上述问题,提出一种融合时序...现有的大多数兴趣点(point of interest,POI)推荐系统由于忽略了用户签到序列中的顺序行为模式,以及用户的个性化偏好对于POI推荐的影响,导致POI推荐系统性能较低,推荐结果不可靠,进而影响用户体验。为了解决上述问题,提出一种融合时序门控图神经网络的兴趣点推荐方法。运用时序门控图神经网络(temporal gated graph neural network,TGGNN)学习POI embedding;采用注意力机制捕获用户的长期偏好;通过注意力机制融合用户的最新偏好和实时偏好,进而捕获用户的短期偏好。通过自适应的方式结合用户的长期和短期偏好,计算候选POI的推荐得分,并根据得分为用户进行POI推荐。实验结果表明,与现有方法相比,该方法在召回率和平均倒数排名这两项指标上均有较为明显的提升,因此可以取得很好的推荐效果,具有良好的应用前景。展开更多
文摘The conversation machine comprehension(MC)task aims to answer questions in the multi-turn conversation for a single passage.However,recent approaches don’t exploit information from historical conversations effectively,which results in some references and ellipsis in the current question cannot be recognized.In addition,these methods do not consider the rich semantic relationships between words when reasoning about the passage text.In this paper,we propose a novel model GraphFlow+,which constructs a context graph for each conversation turn and uses a unique recurrent graph neural network(GNN)to model the temporal dependencies between the context graphs of each turn.Specifically,we exploit three different ways to construct text graphs,including the dynamic graph,static graph,and hybrid graph that combines the two.Our experiments on CoQA,QuAC and DoQA show that the GraphFlow+model can outperform the state-of-the-art approaches.
基金This work is supported by Shenzhen Science and Technology Program,China(RCBS20221008093305007 and 20231115141459001)Young Elite Scientists Sponsorship Program by CAST(2023QNRC001),China.
文摘Sampling-based path planning is widely used in robotics,particularly in high-dimensional state spaces.In the path planning process,collision detection is the most time-consuming operation.Therefore,we propose a learning-based path planning method that reduces the number of collision checks.We develop an efficient neural network model based on graph neural networks.The model outputs weights for each neighbor based on the obstacle,searched path,and random geometric graph,which are used to guide the planner in avoiding obstacles.We evaluate the efficiency of the proposed path planning method through simulated random worlds and real-world experiments.The results demonstrate that the proposed method significantly reduces the number of collision checks and improves the path planning speed in high-dimensional environments.
基金supported by the National Natural Science Foundation of China(61732018,61872335,61802367,61876215)the Strategic Priority Research Program of Chinese Academy of Sciences(XDC05000000)+1 种基金Beijing Academy of Artificial Intelligence(BAAI),the Open Project Program of the State Key Laboratory of Mathematical Engineering and Advanced Computing(2019A07)the Open Project of Zhejiang Laboratory,and a grant from the Institute for Guo Qiang,Tsinghua University.Recommended by Associate Editor Long Chen.
文摘Graph convolutional networks(GCNs)have received significant attention from various research fields due to the excellent performance in learning graph representations.Although GCN performs well compared with other methods,it still faces challenges.Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs.Therefore,motivated by an urgent need in terms of efficiency and scalability in training GCN,sampling methods have been proposed and achieved a significant effect.In this paper,we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN.To highlight the characteristics and differences of sampling methods,we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories.Finally,we discuss some challenges and future research directions of the sampling methods.
基金partially supported by the National Key Research and Development Program of China(2020YFB2104001)。
文摘The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the spotlight.Most existing frameworks typically utilize separate modules for spatial and temporal correlations modeling.However,this stepwise pattern may limit the effectiveness and efficiency in spatial-temporal feature extraction and cause the overlook of important information in some steps.Furthermore,it is lacking sufficient guidance from prior information while modeling based on a given spatial adjacency graph(e.g.,deriving from the geodesic distance or approximate connectivity),and may not reflect the actual interaction between nodes.To overcome those limitations,our paper proposes a spatial-temporal graph synchronous aggregation(STGSA)model to extract the localized and long-term spatial-temporal dependencies simultaneously.Specifically,a tailored graph aggregation method in the vertex domain is designed to extract spatial and temporal features in one graph convolution process.In each STGSA block,we devise a directed temporal correlation graph to represent the localized and long-term dependencies between nodes,and the potential temporal dependence is further fine-tuned by an adaptive weighting operation.Meanwhile,we construct an elaborated spatial adjacency matrix to represent the road sensor graph by considering both physical distance and node similarity in a datadriven manner.Then,inspired by the multi-head attention mechanism which can jointly emphasize information from different r epresentation subspaces,we construct a multi-stream module based on the STGSA blocks to capture global information.It projects the embedding input repeatedly with multiple different channels.Finally,the predicted values are generated by stacking several multi-stream modules.Extensive experiments are constructed on six real-world datasets,and numerical results show that the proposed STGSA model significantly outperforms the benchmarks.
基金Supported by the National High Technology Research and Development Program of China(20-H863-05-XXX-XX)the National Natural Science Foundation of China(61171131)+1 种基金Shandong Province Key Research and Development Program(YD01033)the China Scholarship Council Program(201608370049)。
文摘Numerous meta-learning methods focus on the few-shot learning issue,yet most of them assume that various tasks have a shared embedding space,so the generalization ability of the trained model is limited.In order to solve the aforementioned problem,a task-adaptive meta-learning method based on graph neural network(TAGN) is proposed in this paper,where the characterization ability of the original feature extraction network is ameliorated and the classification accuracy is remarkably improved.Firstly,a task-adaptation module based on the self-attention mechanism is employed,where the generalization ability of the model is enhanced on the new task.Secondly,images are classified in non-Euclidean domain,where the disadvantages of poor adaptability of the traditional distance function are overcome.A large number of experiments are conducted and the results show that the proposed methodology has a better performance than traditional task-independent classification methods on two real-word datasets.
